| FMRS | 63 / 100 · C | 77 / 100 · B | 75 / 100 · B |
| Reliability | 9 / 20 | 12 / 20 | 13 / 20 |
|---|
| Security and permissions | 15 / 20 | 16 / 20 | 12 / 20 |
|---|
| Maintenance | 11 / 20 | 16 / 20 | 16 / 20 |
|---|
| Documentation | 16 / 20 | 18 / 20 | 17 / 20 |
|---|
| Setup experience | 12 / 20 | 15 / 20 | 17 / 20 |
| Best for | - Organizations that need centralized visibility into Okta-related internal access.
- Teams that want MCP clients to assist with permission discovery and pending request submission.
- Operators able to configure Cloudflare Access or OIDC for an Access deployment.
| - Hevy PRO users who want AI assistants to directly access their workout data
- People who prefer using MCP clients like Claude, Cursor, Codex for fitness tracking
- Anyone needing summaries and insights from their training data
| - Scenarios needing clean, structured web context fed to an AI assistant
- Users already on the Firecrawl platform who want to call its scraping capability directly via MCP
|
| Not for | - Workflows requiring MCP to approve or reject requests.
- Workflows requiring direct MCP mutation of groups, roles, or apps.
- Users without an Access deployment, Okta data, or a supported authentication setup.
| - Users without a Hevy PRO subscription (API key required)
- Users who want to use the server without an API key
- Those needing delete workflows (Hevy API does not expose delete endpoints)
| - Simple static-page scraping where you don't want to depend on a third-party API and incur call costs
- Sites that explicitly disallow automated access (robots.txt)
|
| Required permissions | - Access to the Okta API is required; development setup calls for Group Admin and Application Admin roles plus group-management permissions.
- Production deployments require Cloudflare Access or OIDC authentication.
- MCP tools require read_all or create_requests scopes, while Access authorization rules still apply to each operation.
| - Requires HEVY_API_KEY environment variable for Hevy API authentication
- Can create, update, and replace workouts, routines, folders, templates, and body measurements via tools
- Read operations can fetch workouts, routines, folders, templates, history, and user info
| - Requires a Firecrawl API key to call; cost and quota are governed by the Firecrawl account
- firecrawl_agent/firecrawl_interact perform automated browser interaction, which may trigger login or form-submission flows on the target site
|
| Risks and side effects | - A misconfigured Okta API token may grant excessive group or application administration privileges.
- Tokens without an explicit scope receive read_all and create_requests by default; operators can configure read-only or fail-closed behavior.
- Enabling MCP allows authenticated clients to read access data and submit pending requests.
- Incorrect proxy Host or OIDC callback configuration can create redirect-URI risks; the source recommends ALLOWED_HOSTS and OIDC_OVERWRITE_REDIRECT_URI.
| - API key can be misused if leaked; do not expose in URLs, logs, or screenshots
- Create operations may produce duplicates on retry; update operations replace existing records
- The server sends data to the Hevy API and may send telemetry to external services unless disabled
| - Bulk crawl/map tools can generate significant request volume against a target site — respect the site's rate limits and terms of service
- firecrawl_agent's interactive action chain is longer — define task boundaries clearly before running it to avoid accidentally triggering actions on a sensitive site
|
| Supported clients | Claude Code, Claude.ai, Cursor, Zed, Self-hosted models | Claude Desktop, Cursor, Codex, Google Antigravity | Claude Desktop, VS Code, Cursor, Windsurf, Zed, Amp |
| Tools | 3 | 26 | 11 |